Files
FableForge-1.5B/.eval_results/non_nexus_benchmark.yaml

10 lines
326 B
YAML
Raw Permalink Normal View History

- dataset:
id: fableforge-ai/non-nexus-benchmark
task_id: default
value: 94.2
date: "2026-07-06"
source:
url: https://huggingface.co/fableforge-ai/FableForge-1.5B
name: "Non-NEXUS Benchmark"
notes: "45 prompts across 5 categories: general knowledge, uncensored, reasoning, tool use, hardware commands"